CN115618021A - Method and device for recommending suitable planting area of crop variety - Google Patents
Method and device for recommending suitable planting area of crop variety Download PDFInfo
- Publication number
- CN115618021A CN115618021A CN202211630076.3A CN202211630076A CN115618021A CN 115618021 A CN115618021 A CN 115618021A CN 202211630076 A CN202211630076 A CN 202211630076A CN 115618021 A CN115618021 A CN 115618021A
- Authority
- CN
- China
- Prior art keywords
- variety
- planting
- area
- unit area
- data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 63
- 238000012360 testing method Methods 0.000 claims abstract description 61
- 238000012549 training Methods 0.000 claims abstract description 38
- 239000013598 vector Substances 0.000 claims description 50
- 239000011159 matrix material Substances 0.000 claims description 17
- 230000006870 function Effects 0.000 claims description 16
- 238000004364 calculation method Methods 0.000 claims description 11
- 238000012216 screening Methods 0.000 claims description 11
- 230000003993 interaction Effects 0.000 claims description 10
- 238000003860 storage Methods 0.000 claims description 7
- 238000004590 computer program Methods 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 6
- 238000004458 analytical method Methods 0.000 claims description 5
- 238000004422 calculation algorithm Methods 0.000 claims description 5
- 238000010276 construction Methods 0.000 claims description 4
- 238000007621 cluster analysis Methods 0.000 claims description 3
- 239000002131 composite material Substances 0.000 claims description 3
- 238000012795 verification Methods 0.000 claims description 3
- 230000008569 process Effects 0.000 abstract description 4
- 230000010365 information processing Effects 0.000 abstract description 2
- 230000000875 corresponding effect Effects 0.000 description 16
- 239000002689 soil Substances 0.000 description 10
- 238000003306 harvesting Methods 0.000 description 7
- 238000000605 extraction Methods 0.000 description 6
- 238000009331 sowing Methods 0.000 description 6
- 238000004891 communication Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 230000007613 environmental effect Effects 0.000 description 4
- 241000209149 Zea Species 0.000 description 2
- 235000005824 Zea mays ssp. parviglumis Nutrition 0.000 description 2
- 235000002017 Zea mays subsp mays Nutrition 0.000 description 2
- 238000009395 breeding Methods 0.000 description 2
- 230000001488 breeding effect Effects 0.000 description 2
- 235000005822 corn Nutrition 0.000 description 2
- 238000009826 distribution Methods 0.000 description 2
- 230000004927 fusion Effects 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000007781 pre-processing Methods 0.000 description 2
- 208000035240 Disease Resistance Diseases 0.000 description 1
- 241000196324 Embryophyta Species 0.000 description 1
- 241001235534 Graphis <ascomycete fungus> Species 0.000 description 1
- 102000002274 Matrix Metalloproteinases Human genes 0.000 description 1
- 108010000684 Matrix Metalloproteinases Proteins 0.000 description 1
- 238000007476 Maximum Likelihood Methods 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000004913 activation Effects 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 238000013523 data management Methods 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000004720 fertilization Effects 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 238000010899 nucleation Methods 0.000 description 1
- 238000001556 precipitation Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 239000002881 soil fertilizer Substances 0.000 description 1
- 241000894007 species Species 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000002195 synergetic effect Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
- 229920003169 water-soluble polymer Polymers 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/35—Clustering; Classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/02—Agriculture; Fishing; Forestry; Mining
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Life Sciences & Earth Sciences (AREA)
- Marine Sciences & Fisheries (AREA)
- Human Resources & Organizations (AREA)
- Animal Husbandry (AREA)
- Computational Linguistics (AREA)
- Mining & Mineral Resources (AREA)
- Animal Behavior & Ethology (AREA)
- Health & Medical Sciences (AREA)
- Economics (AREA)
- General Health & Medical Sciences (AREA)
- Agronomy & Crop Science (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention provides a method and a device for recommending an area suitable for planting of crop varieties, belonging to the field of agricultural intelligent information processing and comprising the following steps: constructing a geographical environment knowledge map of the area to be analyzed according to the geographical environment data, the variety test data and the planting mode data; constructing a recommendation model according to the knowledge graph and the variety test data and training; inputting each variety to be analyzed and the suitability category of the corresponding planted unit area into a recommendation model, and outputting the suitability category of each variety in the unwanted unit area; and determining a recommended planting unit area set of each variety to be analyzed according to the suitability categories of all the unit areas. The suitability of each variety to the unit area in the recommendation model of the method can be continuously expanded from the determined suitable unit area of the variety, the suitable planting unit area of the variety is continuously expanded in an iterative manner along the link between the entities in the knowledge graph, and the accurate recommendation of the small-scale geographic area in the variety popularization process is realized.
Description
Technical Field
The invention relates to the field of agricultural intelligent information processing, in particular to a method and a device for recommending an area suitable for planting of crop varieties.
Background
The seed industry is a strategic and basic core industry, and the seeds are agricultural 'chips' and are directly related to the grain yield. With the increasing number of main crops breeding and the increasing breeding capability, the number of crop varieties approved or registered each year is rapidly increased.
However, the rapid increase of the number of the crop varieties also brings a series of problems to the popularization and application of the crop varieties. Firstly, with the rapid increase of the number of new varieties of crops in the market, farmers are faced with the problems of difficult selection of suitable varieties, difficult popularization of varieties in agricultural departments and the like; secondly, the labeling of the proper planting areas of a plurality of varieties is too broad and broad or even unclear at present, so that the proper planting areas labeled at the time of variety examination cannot be completely matched with the actual proper planting areas; in addition, due to the influence of heterogeneity of terrain and climate, even in the same ecological region, the environmental conditions in different regions often have great difference, so that the approved varieties are not completely suitable for planting in any region in the participating ecological region.
In actual work, due to the limitation of factors such as personnel, expenses, management mechanisms and the like, the number of test points of a variety region test cannot be greatly increased in a short period, and great challenges are brought to small-scale accurate evaluation of a suitable planting region of the variety. Therefore, a method for recommending a suitable planting area of a crop variety is urgently needed to meet the practical requirement of accurate popularization of the suitable planting area of the current crop variety.
Disclosure of Invention
Aiming at the problems in the prior art, the invention provides a method and a device for recommending an area suitable for planting of crop varieties.
The invention provides a method for recommending an area suitable for planting of crop varieties, which comprises the following steps: acquiring geographic environment data, variety test data and planting mode data of each unit area in an area to be analyzed; wherein the region to be analyzed includes a plurality of unit regions; constructing a geographical environment knowledge graph of the area to be analyzed according to the geographical environment data, the variety test data and the planting mode data; according to the knowledge graph, a variety suitable planting area recommendation model based on an embedded model and knowledge graph reasoning is constructed by combining the variety test data, and the variety suitable planting area recommendation model is trained; inputting the planting record data of each variety to be analyzed in the planted unit area and the corresponding suitability category into the recommended model of the variety suitable planting area, and outputting the suitability category of each variety to be analyzed in each unwanted unit area; determining a recommended planting unit area set of each variety to be analyzed according to the suitability categories of all unit areas; and the model for recommending the planting area suitable for the variety is obtained by performing continuous iterative training according to the relationship among the unit areas in the geographical environment knowledge graph and the suitability category of each variety in the planted unit area as training data.
According to the method for recommending the crop variety suitable planting area, which is provided by the invention, the geographical environment knowledge map of the area to be analyzed is constructed according to the geographical environment data, the variety test data and the planting mode data, and the method comprises the following steps: extracting key geographic environment factors influencing the yield or quality of the crop variety through clustering analysis and relevance analysis; extracting knowledge from the geographic environment data based on the key geographic environment factor; after the verification of the extracted knowledge is passed, expressing the extracted knowledge by adopting a triple, and establishing a corresponding composite index; and expanding the triples extracted according to the geographic environment data by using the planting mode data to obtain expanded triples, and constructing a geographic environment knowledge graph of the area to be analyzed according to the expanded triples.
According to the method for recommending the crop variety suitable planting area, provided by the invention, a variety suitable planting area recommendation model based on an embedded model and knowledge graph reasoning is constructed according to the knowledge graph and by combining the variety test data, and the variety suitable planting area recommendation model is trained, and the method comprises the following steps: determining the suitability category of each test variety in the planted unit area according to the variety test data of each unit area and the corresponding preset index threshold, and taking the variety test data and the corresponding suitability category of each unit area as planting record data for training a recommendation model of the planting area where the variety is suitable; generating each-order unit region expansion set of each variety according to the knowledge graph and the planting record data of each variety; representing each unit area as a candidate unit area vector by using an embedding representation method, and determining a variety embedding vector obtained after each variety is expanded in the initial planting unit area according to the relation between the entities in the knowledge graph; calculating the suitability probability between the variety embedding vector and the candidate unit region vector, determining the suitability category of the variety in the unit region according to a preset index threshold, and training the recommendation model of the planting region suitable for the variety according to the suitability category of the variety in the unit region.
According to the method for recommending the suitable planting area of the crop variety, provided by the invention, the variety embedding vector obtained after the initial planting unit area of each variety is expanded is determined according to the relation among the entities in the knowledge map and the expansion set of the unit area of each step of the variety, and the method comprises the following steps: according to the candidate unit areaEmbedded vector ofAnd varieties ofFirst order unit area extension set ofEach triplet of (a)Calculating candidate unit regionsAnd entitiesIn a relationProbability of similarity of:
wherein ,andrespectively first order unit area expansion setGo to the firstRelationships in triplesAnd a header entityAn embedded representation of (a);representing embedded representation vectors orThe dimension of the matrix;andrespectively represent an extended setOf each tripleAnd a head entityA corresponding embedded representation;
variety calculationVector of potentially suitable unit areas on a first-order unit area extension setThe calculation method comprises the following steps:
will be provided withIs assigned to the vectorRecalculate, recalculateAnd entitiesIn a relationProbability of similarity ofFurther obtaining the varietyVector of potentially suitable cell regions on a second-order cell region extension set(ii) a Repeating the above steps to obtain the varietyIn thatVector of potentially suitable unit regions on extended set of order unit regions,(ii) a According to the varietyVectors over extended sets of unit regions of various ordersDetermining the varietyIn the unit areaThe expanded variety embedding vector。
According to the method for recommending the crop variety suitable planting area, the training of the model for recommending the crop variety suitable planting area comprises the following steps of:
wherein ,andthe embedded matrices for all planting records and entities respectively,is a relationship ofThe embedded matrix of (a) is embedded in the matrix,for relationships in a knowledge-graphIs indicative of tensorThe slice of (2) is cut into pieces,represents the L2 norm;is variety-unit area interaction matrix, if varietyIn the unit areaIs suitable, thenOtherwise, otherwise;、Is a preset constant;representing a knowledge graphThe set of relationships in (1);the function is activated for sigmoid.
According to the method for recommending the crop variety suitable planting area, the training of the model for recommending the crop variety suitable planting area comprises the following steps: iterative solution of a loss function is carried out by adopting a random gradient descent algorithm; in each iterative calculation, the interaction matrix is randomly calculated according toAnd knowledge-graphExtracting positive and negative samples, and calculating、Andand then updates the gradient of、Andthe value of (c).
According to the method for recommending the suitable planting area of the crop variety, after the recommended planting unit area set of each variety to be analyzed is determined, the method further comprises the following steps: obtaining a final suitable planting area of each variety after secondary screening according to the recommended planting unit area set of each variety; wherein the characteristics of the secondary screening include: variety resistance, historical average yield per mu of the variety and the number of the variety in a unit area.
The invention also provides a device for recommending the suitable planting area of the crop variety, which comprises: the data acquisition module is used for acquiring geographic environment data, variety test data and planting mode data of each unit area in the area to be analyzed; wherein the region to be analyzed includes a plurality of unit regions; the knowledge map construction module is used for constructing a geographical environment knowledge map of an area to be analyzed according to the geographical environment data, the variety test data and the planting mode data; the model processing module is used for constructing a variety suitable planting area recommendation model based on embedded model and knowledge map reasoning according to the knowledge map and by combining the variety test data, and training the variety suitable planting area recommendation model; the result output module is used for inputting the planting record data of each variety to be analyzed in the planted unit area and the corresponding suitability category into the variety suitability planting area recommendation model and outputting the suitability category of each variety to be analyzed in each non-planted unit area; determining a recommended planting unit area set of each variety to be analyzed according to the suitability categories of all unit areas; and the model for recommending the planting area suitable for the variety is obtained by performing continuous iterative training according to the relationship among the unit areas in the geographical environment knowledge graph and the suitability category of each variety in the planted unit area as training data.
The invention also provides an electronic device comprising a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the processor executes the program to realize the method for recommending the suitable planting area of the crop variety.
The present invention also provides a non-transitory computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements a method of recommending a suitable planting area for a crop variety as recited in any of the above.
According to the method and the device for recommending the crop variety suitable planting area, provided by the invention, in the recommendation model, based on the link relation between the entities of each unit area in the knowledge map, the suitability of each variety to the unit area is continuously expanded from the determined suitable unit area of the variety, namely, the suitable planting unit area of the variety is continuously and iteratively expanded along the link between the entities in the knowledge map, so that the accurate recommendation of the small-scale geographical area in the crop variety popularization process is realized.
Drawings
In order to more clearly illustrate the technical solutions of the present invention or the prior art, the drawings needed for the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and those skilled in the art can also obtain other drawings according to the drawings without creative efforts.
FIG. 1 is a schematic flow chart of a method for recommending an area suitable for planting a crop variety provided by the invention;
FIG. 2 is a schematic structural diagram of a device for recommending an area suitable for planting crop varieties, provided by the invention;
fig. 3 is a schematic structural diagram of an electronic device provided in the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings, and it is obvious that the described embodiments are some, but not all embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The following describes a method and apparatus for recommending an appropriate crop variety planting area according to the present invention with reference to fig. 1 to 3. Fig. 1 is a schematic flow chart of a method for recommending an area suitable for planting a crop variety according to the present invention, and as shown in fig. 1, the method for recommending an area suitable for planting a crop variety according to the present invention includes:
101. and acquiring geographic environment data, variety test data and planting mode data of each unit area in the area to be analyzed. Wherein the region to be analyzed includes a plurality of unit regions.
For example, the geographic environmental data may include: basic geographic information data, meteorological data, soil data. The basic geographic information data comprise county-level administrative division data and geomorphic data (contour lines and a digital elevation model DEM); the meteorological data comprises meteorological data of national meteorological sites and meteorological data of national and provincial district test sites; the soil data comprises soil fertilizer data and soil biological data.
Alternatively, the basic geographic information data may be obtained from a national geographic information public service platform (heaven and earth map); the meteorological data can be obtained from a meteorological data network and collected from the historical observation data of each district testing site; the soil data can be obtained from data sources such as a national soil information service platform, a Chinese soil science database, a national agricultural science data center, a national soil testing formula fertilization data management platform and the like. The variety test data can be obtained from national crop variety test information and operation management platform, and the planting mode data can be obtained from agricultural rural department and agricultural department websites and agricultural information websites at all levels, and can be obtained through questionnaire survey, literature research, expert consultation and other modes.
The variety test data refers to phenotypic character data obtained after the variety to be analyzed is planted at a test point in the area to be analyzed. In the invention, the variety test data can be phenotype character data collected when the variety to be analyzed is used for developing a national or provincial variety approval test; the variety approval test also comprises a variety region test and a variety production test.
Table 1 shows the data of some varieties in Huang-Huai-Hai summer-sowed corn area; wherein the variety names are "C001" and "C002", the test sites are "Anyang city county" in Henan province and "Yiyi city Pingyi county" in Shandong province, and the part of phenotypic characters are "yield per mu", "seeding period", "growth period", "plant height" and "leaf spot".
TABLE 1
Wherein, the planting mode data comprises a harvesting mode, a sowing mode and a cultivation mode. Optionally, farmer planting preferences may be included.
In this embodiment, the region to be analyzed includes a plurality of unit regions. When the suitable planting area of the variety is recommended, the recommendation is carried out by taking the unit area as a scale. The unit area is the minimum unit for dividing the geographical space of the area to be analyzed, and can be a county-level administrative district or a city-level administrative district.
Optionally, after the geographic environment data is acquired, the method further includes preprocessing the acquired geographic environment data, variety test data and planting mode data based on the unit area, where the preprocessing includes: any one or more of data cleaning, semantic fusion, abnormal value processing, missing value processing, data standardization, data normalization, feature selection and data discretization; the semantic fusion comprises the steps of comprehensively utilizing entity extraction, entity alignment, entity linking, conflict resolution and relationship deduction technologies, carrying out semantic association on geographic environment data of different sources or different formats, and eliminating the heterogeneity among different source data
102. And constructing a geographical environment knowledge graph of the area to be analyzed according to the geographical environment data, the variety test data and the planting mode data.
The geographic environment data and the planting mode data of each unit area can be correlated, extracted into a triple data form, and finally the geographic environment knowledge map of the area to be analyzed is constructed. Each unit area may be an entity, which includes several attributes. Regarding the variety test data, if a certain variety a is easily grown in a certain area L, a certain disease can be introduced as an environmental attribute.
103. And constructing a variety suitable planting area recommendation model based on an embedded model and knowledge graph reasoning according to the knowledge graph and by combining the variety test data, and training the variety suitable planting area recommendation model.
And the model for recommending the planting area suitable for the variety is obtained by performing continuous iterative training according to the relationship among the unit areas in the geographical environment knowledge graph and the suitability category of each variety in the planted unit area as training data.
The suitability category can be divided as required, for example, the suitability category can be divided into 2 types: suitable and unsuitable, indicated by the numbers 1 and 0, respectively. Specifically, the indexes of the yield, resistance and quality traits are used as the basis for dividing the suitability categories, and the suitability category of each variety in the tested planting unit area is determined according to a preset index threshold and variety test data. For example: the comparison yield increase percentage (%) "and the" disease resistance "can be used as the basis for the classification of the suitability categories, and the classification rule is as follows: the yield of the control variety is increased by more than or equal to 3 percent and the resistance is more than or equal to the resistance, and the control variety is marked as appropriate; otherwise it is not suitable. For example: both the variety a and the variety B were subjected to the variety test in the "unit area #1", wherein the yield of the variety a was increased by 5% as compared with the control variety and the resistance was high, and the yield of the variety B was decreased by 2% as compared with the control variety and the resistance was high, and then the suitability category of the variety a in the unit area #1 was "suitable" and the suitability category of the variety B in the unit area #1 was "unsuitable".
104. Inputting the planting record data of each variety to be analyzed in the planted unit area and the corresponding suitability category into the variety suitability planting area recommendation model, and outputting the suitability category of each variety to be analyzed in each non-planted unit area; and determining a recommended planting unit area set of each variety to be analyzed according to the suitability category of each variety to be analyzed in each unit area.
Wherein, the planting recorded data corresponds to the variety test data in the above 101, that is, the same type of data is adopted. Optionally, after 104, outputting the final recommendation result to the user according to the user query request. The input mode of the user query request comprises the following steps: graphical interface input, voice input, touch screen clicking, and program interface calling. The recommendation result comprises the following steps: the method comprises the steps of specifying a suitable planting unit area of a variety, specifying a suitable planting variety of the unit area, and presenting results in a visual display mode based on an electronic map, a character display mode, a voice broadcast mode, and JSON or XML format package data.
For example: the user can use the smart device to perform voice questioning: after the system which is the proper planting area of the 'Zhengdan 958' of the corn variety receives the voice query request, the system returns the recommended planting area data of the 'Zhengdan 958' calculated by the system and carries out voice broadcast, or the proper planting area of the variety is visually displayed on a screen by utilizing an electronic map.
According to the method for recommending the suitable planting area of the crop variety, in the recommendation model, based on the link relation among the entities of each unit area in the knowledge graph, the suitability of each variety to the unit area is continuously expanded from the determined suitable unit area of the variety, namely, the suitable planting unit area of the variety is continuously expanded in an iterative manner along the link among the entities in the knowledge graph, so that the accurate recommendation of the small-scale geographical area in the popularization process of the crop variety is realized.
In one embodiment, the constructing a geographical environment knowledge graph of an area to be analyzed according to the geographical environment data, the variety test data and the planting manner data includes: extracting key geographical environment factors influencing the yield or quality of the crop variety through cluster analysis and relevance analysis; extracting knowledge from the geographic environment data based on the key geographic environment factor; after the verification of the extracted knowledge is passed, expressing the extracted knowledge by adopting a triple, and establishing a corresponding composite index; and expanding the triples extracted according to the geographic environment data by using the planting mode data to obtain expanded triples, and constructing a geographic environment knowledge map about each unit area according to the expanded triples.
The knowledge extraction comprises entity extraction, attribute extraction, relation extraction, event extraction and entity linkage.
Optionally, in this embodiment of the present invention, through cluster analysis and relevance analysis, the selected key geographic environment factor set includes: effective accumulated temperature, sunshine duration, average air temperature, lowest air temperature, highest air temperature, earth surface temperature, maximum wind power, average precipitation, average humidity, photo-thermal ratio, soil type and soil texture.
Optionally, when some index values of the geographic environmental factors in a certain unit area are missing, a spatial interpolation method may be used for completion, where the spatial interpolation method includes: any one or more of a kriging interpolation method, an inverse distance weighted interpolation method, a natural neighbor interpolation method, and a nearest neighbor interpolation method.
Generally, the specific representation of a triplet is: (entity, relationship, entity), (entity, attribute value), (entity, relationship, event), (event, relationship, event). For example: the "effective integrated temperature" of "unit region #1" is "2500 ℃", which can be represented by a triplet: (unit region #1, effective integrated temperature, 2500 ℃); wherein, the unit area #1 is an entity, the effective accumulated temperature is an attribute (key geographic environment factor), and 2500 ℃ is an attribute value.
And then, extending the triples extracted based on the geographic environment data by using the planting mode data to obtain the extended triples.
The factors such as the harvesting mode, the sowing mode, the cultivation mode, the farmer planting preference and the like of the area to be analyzed can be taken into consideration and expressed in a triple form. For example: the "sowing mode" of the "unit area #1" is "machine sowing", and the "harvesting mode" of the "unit area #2" is "machine harvesting", then the above two pieces of knowledge can be represented by the three groups respectively: (cell region #1, sowing mode, machine sowing), (cell region #1, harvesting mode, machine harvesting).
And then, constructing a geographical environment knowledge graph of the area to be analyzed by using the expanded triple.
In one embodiment, the constructing a recommended region for cultivar-suitable planting model based on embedded model and knowledge-map inference according to the knowledge-map and in combination with the cultivar test data, and training the recommended region for cultivar-suitable planting model includes: determining the suitability category of each test variety in the planted unit area according to the variety test data of each unit area and the corresponding preset index threshold; taking the variety test data and the corresponding suitability category of each unit area as planting record data for training a recommendation model of the planting area where the variety is suitable; generating each-order unit area expansion set of each variety according to the knowledge graph and the planting record data of each variety; representing each unit area as a candidate unit area vector by using an embedding representation method, and determining a variety embedding vector obtained after each variety is expanded in the initial planting unit area according to the relation between the entities in the knowledge graph; calculating a fitness probability between the variety embedding vector and the candidate unit region vectorAnd determining the suitability type of the variety in the unit area according to a preset index threshold, and training a recommendation model of the planting area where the variety is suitable according to the suitability type of the variety in the unit area.
Variety of (IV) CIs/are as followsOrder unit area expansion setIs indicated byThe set formed for the triples of the head entity is denoted as,Is a preset positive integer.
Wherein a knowledge-graph is givenAnd interaction matrixVariety of (ii)IsThe order association unit area entity is expressed asIs marked as。
Is variety ofThe set of planting records of (1) representing the varietyAn initial planting unit area for performing suitability unit area expansion on the knowledge graph;is a set of three-element data,,,respectively representing head, relationship and tail entities in the triples, whereinAndrespectively represent knowledge graphsThe entity set and the relationship set in (1);positive integers specified for the system.
Cell area interaction matrix: variety of the same speciesIn the unit areaIs a suitable rule(ii) a Otherwise. wherein ,represents a collection of species to be analyzed,represents a set of unit areas to be recommended,is a geographical environment knowledge map of the area to be analyzed.
According to the knowledge-graphTaking the planting record of each variety as an initial seed unit area for the suitability expansion of the variety, and further generating a potentially suitable unit area expansion set of each order for each variety。
Representing each unit area as a vector using an embedded representation( wherein ,is a vectorDimension of (c) from a knowledge-graphThe relationship among the entities obtains the embedded vector of each variety obtained after the initial seed unit area of each variety is expanded。
Specifically, when the variety or the unit area is embedded and represented, the one-hot coding and the attributes, the bag-of-words model, the context information and the like of the object to be represented can be comprehensively used for vector representation. For example: when the unit area is embedded and expressed, the elements such as the one-hot code, the effective accumulated temperature, the sunshine duration, the highest temperature, the average humidity, the soil type, the harvesting mode, the cultivation mode and the like can be considered to be integrated and converted into a numerical vector.
Finally, calculating the varietyEmbedded vector ofCandidate unit areaVector of (2)Suitable probability of betweenDetermining the suitability class of the variety in the unit area according to a preset threshold value; wherein,the calculation formula of (2) is as follows:
Preferably, the threshold of the activation function can be set to 0.5 ifIf the value of (A) is greater than 0.5, the variety is consideredIn the unit areaPlanting properly; otherwise, the variety is consideredIs not suitable for the unit areaPlanting in the interior.
In one embodiment, the determining, according to the relationship between the entities in the knowledge-graph and the extension sets of the unit areas of the respective levels of the variety, a variety embedding vector obtained after the initial planting unit area of each variety is extended includes: according to the candidate unit areaEmbedded vector ofAnd varieties thereofFirst order unit area extension set ofEach triplet of (a)Calculating candidate unit regionsAnd entitiesIn a relationProbability of similarity of:
wherein ,andrespectively, a first order cell region extension setTo go toRelationships among triplesAnd a header entityAn embedded representation of (a);represents the dimensions of the embedded representation (vector or matrix);andrespectively represent an extended setOf each tripleAnd a head entityA corresponding embedded representation;
variety calculationVector of potentially suitable unit areas on a first order unit area extension setThe calculation method comprises the following steps:
Will be provided withValue of (2) to a vectorRecalculate, recalculateAnd entitiesIn a relationProbability of similarity ofFurther obtaining the varietyVector of potentially suitable cell regions on a second order cell region extension set(ii) a Repeating the above steps to obtain the varietyIn thatVectors of potentially suitable unit regions on an extended set of order unit regions,(ii) a According to varietyVectors over extended sets of unit regions of respective ordersDetermining the varietyIn the unit areaThe expanded variety embedding vector。
In one embodiment, the training of the breed-appropriate planting area recommendation model includes training of the breed-appropriate planting area recommendation model according to the following loss function:
wherein ,andan embedded matrix of all planting records and entities respectively,is a relationship ofThe embedded matrix of (a) is embedded,for relationships in a knowledge graphIs indicative of tensorThe slice of (2) is cut into pieces,represents the L2 norm;is variety-unit area interaction matrix, if varietyIn the unit areaIs suitable, thenOtherwise;、Is a preset constant;representing a knowledge graphThe set of relationships in (1);the function is activated for sigmoid.Andare respectively asA predetermined constant, preferably, the value of which can be set to,。
At a given knowledge-graphAnd variety-unit area interaction matrixIn the case of (2), the model parameters can be optimized by maximizing the model parametersThe posterior probability of (2) is used for carrying out iterative training of the model, and the objective function is as follows:
according to bayes' theorem, the above formula can be converted into:
wherein the parametersSubject to a normal distribution, i.e.;The probability product for each fact in the knowledge-graph is:
to be at given parametersAnd knowledge mapThe maximum likelihood function of (a) can be defined as the product of the bernoulli distributions:
wherein ,when triplets are used to indicate functionsWhen the water-soluble polymer is existed in the water,has a value of 1; otherwise, the value of the function is 0;andsuper parameters of the model respectively;the function is activated for sigmoid.
Will be provided withTaking the negative logarithm, the above-mentioned loss function of the model can be obtained,
in one embodiment, the training of the variety suitability planting area recommendation model comprises: iterative solution of a loss function is carried out by adopting a random gradient descent algorithm; in each iteration calculation, the interaction matrix is randomly selected according toAnd knowledge mapExtracting positive and negative samples, and calculating、Andand then updates the gradient of、Andthe value of (c).
Preferably, the iterative solution of the loss function can be performed using a stochastic gradient descent algorithm. In each iteration calculation, small random batches can be obtained according to the interaction matrixAnd knowledge-graphExtracting positive and negative samples, and calculating、Andand then updates the gradient of、Andthe value of (c). In order to facilitate the programming implementation of the solution algorithm, the programming implementation of the model can be performed on the basis of the existing machine learning development framework (such as TensorFlow, pyTorch, paddlePaddlet, and the like).
In one embodiment, after determining the set of recommended planting unit areas for each variety to be analyzed, the method further comprises: obtaining a final suitable planting area of each variety after secondary screening according to the recommended planting unit area set of each variety; wherein the characteristics of the secondary screening include: variety resistance, historical average yield per mu of the variety and the number of the variety in a unit area.
And the secondary screening is to perform secondary screening on the preliminary recommended planting unit area set of each variety based on a series of predefined rules, so as to obtain a final suitable planting area combination. Specifically, secondary screening characteristics can be determined according to the variety, the unit area and the synergistic relationship between the variety and the unit area, and relevant screening characteristics include: variety resistance, historical average yield per mu of the variety and the number of the varieties in a unit area. For example: part of varieties in each unit area can be removed according to variety resistance or historical per mu yield; then, the suitable planting unit area set of each variety is summarized again according to the variety dimension, and the set is recommended as the suitable planting area of the variety. Specifically, the secondary screening rule is as follows: (a) In a certain designated unit area, sorting according to the comprehensive resistance of varieties from large to small, and selecting varieties larger than a designated threshold; (b) In a certain designated unit area, sorting the varieties according to the historical average yield per mu of the varieties from large to small, and selecting the varieties larger than a designated threshold value; (c) Obtaining the intersection of the varieties in the rules a and b to obtain the recommended varieties of the designated unit area, and obtaining the recommended varieties of all the unit areas in the same way; (d) And summarizing the suitable planting area of each variety according to the variety dimension, and recommending the suitable planting area.
The following describes the apparatus for recommending a suitable crop variety planting area according to the present invention, and the apparatus for recommending a suitable crop variety planting area described below and the method for recommending a suitable crop variety planting area described above may be referred to with respect to each other.
Fig. 2 is a schematic configuration diagram of a crop variety suitable planting area recommendation device according to the present invention, and as shown in fig. 2, the crop variety suitable planting area recommendation device includes: the system comprises a data acquisition module 201, a knowledge graph construction module 202, a model processing module 203 and a result output module 204. The data acquisition module 201 is used for acquiring geographic environment data, variety test data and planting mode data of each unit area in an area to be analyzed; wherein the region to be analyzed includes a plurality of unit regions; the knowledge graph construction module 202 is configured to construct a geographical environment knowledge graph of the area to be analyzed according to the geographical environment data, the variety test data and the planting mode data; the model processing module 203 is used for constructing a recommended region model for the suitable variety planting based on an embedded model and knowledge graph reasoning according to the knowledge graph and by combining the variety test data, and training the recommended region model for the suitable variety planting; the result output module 204 is used for inputting the planting record data of each variety to be analyzed in the planted unit area and the corresponding suitability category into the variety suitability planting area recommendation model and outputting the suitability category of each variety to be analyzed in each non-planted unit area; determining a recommended planting unit area set of each variety to be analyzed according to the suitability categories of all the unit areas; and the model for recommending the planting area suitable for the variety is obtained by performing continuous iterative training according to the relationship among the unit areas in the geographical environment knowledge graph and the suitability category of each variety in the planted unit area as training data.
The device embodiment provided in the embodiments of the present invention is for implementing the above method embodiments, and for details of the process and the details, reference is made to the above method embodiments, which are not described herein again.
The implementation principle and the generated technical effects of the recommending device of the suitable crop variety planting area provided by the embodiment of the invention are the same as those of the recommending method of the suitable crop variety planting area, and for the sake of brief description, reference may be made to the corresponding contents in the recommending method of the suitable crop variety planting area.
Fig. 3 is a schematic structural diagram of an electronic device provided in the present invention, and as shown in fig. 3, the electronic device may include: a processor (processor) 301, a communication Interface (Communications Interface) 302, a memory (memory) 303 and a communication bus 304, wherein the processor 301, the communication Interface 302 and the memory 303 communicate with each other through the communication bus 304. Processor 301 may invoke logic instructions in memory 303 to perform a method for recommending a suitable planting area for a crop variety, the method comprising: acquiring geographic environment data, variety test data and planting mode data of each unit area in an area to be analyzed; wherein the region to be analyzed includes a plurality of unit regions; constructing a geographical environment knowledge graph of an area to be analyzed according to the geographical environment data, the variety test data and the planting mode data; according to the knowledge graph, a variety suitable planting area recommendation model based on an embedded model and knowledge graph reasoning is constructed by combining the variety test data, and the variety suitable planting area recommendation model is trained; inputting the planting record data of each variety to be analyzed in the planted unit area and the corresponding suitability category into the variety suitability planting area recommendation model, and outputting the suitability category of each variety to be analyzed in each non-planted unit area; determining a recommended planting unit area set of each variety to be analyzed according to the suitability categories of all the unit areas; and the model for recommending the planting area suitable for the variety is obtained by performing continuous iterative training according to the relationship among the unit areas in the geographical environment knowledge graph and the suitability category of each variety in the planted unit area as training data.
In addition, the logic instructions in the memory 303 may be implemented in the form of software functional units and stored in a computer readable storage medium when the logic instructions are sold or used as independent products. Based on such understanding, the technical solution of the present invention or a part thereof which substantially contributes to the prior art may be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
In yet another aspect, the present invention also provides a non-transitory computer readable storage medium having stored thereon a computer program which when executed by a processor implements a method for recommending a suitable planting area for a crop variety provided by performing the above methods, the method comprising: acquiring geographic environment data, variety test data and planting mode data of each unit area in an area to be analyzed; wherein the region to be analyzed includes a plurality of unit regions; constructing a geographical environment knowledge graph of an area to be analyzed according to the geographical environment data, the variety test data and the planting mode data; according to the knowledge graph, a variety suitable planting area recommendation model based on an embedded model and knowledge graph reasoning is constructed by combining the variety test data, and the variety suitable planting area recommendation model is trained; inputting the planting record data of each variety to be analyzed in the planted unit area and the corresponding suitability category into the variety suitability planting area recommendation model, and outputting the suitability category of each variety to be analyzed in each unplanted unit area; determining a recommended planting unit area set of each variety to be analyzed according to the suitability categories of all the unit areas; and the model for recommending the variety suitable planting area is obtained by performing continuous iterative training according to the relationship among the unit areas in the geographical environment knowledge graph and the suitability category of each variety in the planted unit area as training data.
The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one position, or may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment may be implemented by software plus a necessary general hardware platform, and may also be implemented by hardware. Based on the understanding, the above technical solutions substantially or otherwise contributing to the prior art may be embodied in the form of a software product, which may be stored in a computer-readable storage medium, such as ROM/RAM, magnetic disk, optical disk, etc., and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the method according to the various embodiments or some parts of the embodiments.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (10)
1. A method for recommending an area suitable for planting of a crop variety is characterized by comprising the following steps:
acquiring geographic environment data, variety test data and planting mode data of each unit area in an area to be analyzed; wherein the region to be analyzed includes a plurality of unit regions;
constructing a geographical environment knowledge graph of an area to be analyzed according to the geographical environment data, the variety test data and the planting mode data;
according to the knowledge graph, a variety suitable planting area recommendation model based on an embedded model and knowledge graph reasoning is constructed by combining the variety test data, and the variety suitable planting area recommendation model is trained;
inputting the planting record data of each variety to be analyzed in the planted unit area and the corresponding suitability category into the variety suitability planting area recommendation model, and outputting the suitability category of each variety to be analyzed in each non-planted unit area; determining a recommended planting unit area set of each variety to be analyzed according to the suitability categories of all the unit areas;
and the recommendation model is obtained after continuous iterative training according to the relationship among all unit areas in the geographical environment knowledge graph and the suitability category of each variety in the planted unit area as training data.
2. The method for recommending a suitable planting area for a crop variety as claimed in claim 1, wherein said constructing a geographical knowledge map of the area to be analyzed from said geographical environment data, said variety test data and said planting pattern data comprises:
extracting key geographical environment factors influencing the yield or quality of the crop variety through cluster analysis and relevance analysis;
extracting knowledge from the geographic environment data based on the key geographic environment factor;
after the verification of the extracted knowledge is passed, expressing the extracted knowledge by adopting a triple, and establishing a corresponding composite index;
and expanding the triples extracted according to the geographic environment data by using the planting mode data to obtain expanded triples, and constructing a geographic environment knowledge graph of the area to be analyzed according to the expanded triples.
3. The method for recommending a suitable crop variety planting area according to claim 1 or 2, wherein said constructing a suitable crop variety planting area recommendation model based on an embedded model and knowledge-graph reasoning according to said knowledge-graph in combination with said variety test data and training said suitable crop variety planting area recommendation model comprises:
determining the suitability category of each test variety in the planted unit area according to the variety test data of each unit area and the corresponding preset index threshold, and taking the variety test data of each unit area and the corresponding suitability category as planting record data for training the recommendation model;
generating each-order unit region expansion set of each variety according to the knowledge graph and the planting record data of each variety;
representing each unit area as a candidate unit area vector by using an embedding representation method, and determining a variety embedding vector obtained after each variety is expanded in an initial planting unit area according to the relation between each entity in the knowledge graph and each step area unit area expansion set of each variety;
calculating the suitability probability between the variety embedding vector and the candidate unit region vector, determining the suitability category of the variety in the unit region according to a preset index threshold, and training the recommendation model of the planting region suitable for the variety according to the suitability category of the variety in the unit region.
4. The method for recommending a suitable planting area for a crop variety as claimed in claim 3, wherein said determining a variety embedding vector for each variety after initial planting unit area expansion based on the relationships between entities in said knowledge-graph and the respective set of step-wise area-unit area expansions for each variety comprises:
according to the candidate unit areaEmbedded vector ofAnd varieties thereofFirst order unit area extension set ofEach triplet of (a)Calculating candidate unit regionsAnd entitiesIn a relationProbability of similarity of:;
wherein ,andrespectively first order unit area expansion setTo go toRelationships in triplesAnd a head entityAn embedded representation of (a);representing the dimensions of an embedded representation vector or matrix;andrespectively representing extended setsLast every relation in triplesAnd a head entityA corresponding embedded representation;
variety of calculationVector of potentially suitable unit areas on a first order unit area extension setThe calculation method comprises the following steps:
will be provided withValue of (2) to a vectorRecalculatingAnd entitiesIn a relationProbability of similarity ofFurther obtaining the varietyVector of potentially suitable cell regions on a second order cell region extension set;
Repeating the above steps to obtain the varietyIn thatVectors of potentially suitable unit regions on an extended set of order unit regions,;
5. The method of claim 4, wherein said training of said variety suitable planting area recommendation model comprises training said variety suitable planting area recommendation model according to a loss function as follows:
wherein ,andthe embedded matrices for all planting records and entities respectively,is a relationship ofThe embedded matrix of (a) is embedded,for relationships in a knowledge-graphIs indicated tensorThe slice of (a) is cut,represents the L2 norm;is variety-unit area interaction matrix, if varietyIn the unit areaIs suitable, thenOtherwise, otherwise;、Is a preset constant;representing a knowledge graphThe set of relationships in (1);the function is activated for sigmoid.
6. The method of claim 5, wherein said training of said crop variety suitable planting area recommendation model comprises:
iterative solution of a loss function is carried out by adopting a random gradient descent algorithm;
7. The method of recommending suitable planting areas for crop varieties of claim 1, wherein said determining a set of recommended planting unit areas for each variety to be analyzed further comprises:
obtaining a final suitable planting area of each variety after secondary screening according to the recommended planting unit area set of each variety;
wherein the characteristics of the secondary screening include: variety resistance, historical average yield per mu of the variety and the number of the variety in a unit area.
8. A suitable planting area recommendation device of crops variety, characterized by includes:
the data acquisition module is used for acquiring geographic environment data, variety test data and planting mode data of each unit area in the area to be analyzed; wherein the region to be analyzed includes a plurality of unit regions;
the knowledge map construction module is used for constructing a geographical environment knowledge map of an area to be analyzed according to the geographical environment data, the variety test data and the planting mode data;
the model processing module is used for constructing a variety suitable planting area recommendation model based on embedded model and knowledge map reasoning according to the knowledge map and by combining the variety test data, and training the variety suitable planting area recommendation model;
the result output module is used for inputting the planting record data of each variety to be analyzed in the planted unit area and the corresponding suitability category into the variety suitability planting area recommendation model and outputting the suitability category of each variety to be analyzed in each unwanted unit area; determining a recommended planting unit area set of each variety to be analyzed according to the suitability categories of all unit areas;
and the model for recommending the variety suitable planting area is obtained by performing continuous iterative training according to the relationship among the unit areas in the geographical environment knowledge graph and the suitability category of each variety in the planted unit area as training data.
9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor when executing the program implements a method for recommending an appropriate growing area for a crop variety as defined in any of claims 1 to 7.
10. A non-transitory computer readable storage medium having a computer program stored thereon, wherein the computer program when executed by a processor implements a method for recommending a suitable planting area for a crop variety according to any one of claims 1 to 7.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211630076.3A CN115618021B (en) | 2022-12-19 | 2022-12-19 | Method and device for recommending planting area suitable for crop variety |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211630076.3A CN115618021B (en) | 2022-12-19 | 2022-12-19 | Method and device for recommending planting area suitable for crop variety |
Publications (2)
Publication Number | Publication Date |
---|---|
CN115618021A true CN115618021A (en) | 2023-01-17 |
CN115618021B CN115618021B (en) | 2023-04-28 |
Family
ID=84879893
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202211630076.3A Active CN115618021B (en) | 2022-12-19 | 2022-12-19 | Method and device for recommending planting area suitable for crop variety |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN115618021B (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115860581A (en) * | 2023-02-28 | 2023-03-28 | 北京市农林科学院信息技术研究中心 | Method, device, equipment and storage medium for evaluating suitability of crop variety |
CN116109915A (en) * | 2023-04-17 | 2023-05-12 | 济宁能源发展集团有限公司 | Intelligent recognition method for container door state |
CN117371529A (en) * | 2023-12-07 | 2024-01-09 | 北京市农林科学院信息技术研究中心 | Crop phenotype data knowledge graph generation method and device, electronic equipment and medium |
CN117557399A (en) * | 2024-01-11 | 2024-02-13 | 四川省农村经济综合信息中心 | Salvia miltiorrhiza growth proper distribution area analysis system and analysis method thereof |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104899786A (en) * | 2015-05-13 | 2015-09-09 | 中国农业大学 | Corn variety planting suitability fine dividing method and system thereof |
US20200242444A1 (en) * | 2019-01-30 | 2020-07-30 | Baidu Usa Llc | Knowledge-graph-embedding-based question answering |
US20200302556A1 (en) * | 2019-03-21 | 2020-09-24 | International Business Machines Corporation | Crop recommendation |
CN112149004A (en) * | 2020-10-30 | 2020-12-29 | 中国科学院计算技术研究所 | Personalized recommendation method based on collaborative knowledge map |
CN114332667A (en) * | 2022-03-17 | 2022-04-12 | 北京市农林科学院信息技术研究中心 | Corn plant type identification method and device, electronic equipment and storage medium |
CN114461903A (en) * | 2021-12-29 | 2022-05-10 | 北京市农林科学院信息技术研究中心 | Method and device for determining suitable popularization area of crop variety |
CN114595344A (en) * | 2022-05-09 | 2022-06-07 | 北京市农林科学院信息技术研究中心 | Crop variety management-oriented knowledge graph construction method and device |
-
2022
- 2022-12-19 CN CN202211630076.3A patent/CN115618021B/en active Active
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104899786A (en) * | 2015-05-13 | 2015-09-09 | 中国农业大学 | Corn variety planting suitability fine dividing method and system thereof |
US20200242444A1 (en) * | 2019-01-30 | 2020-07-30 | Baidu Usa Llc | Knowledge-graph-embedding-based question answering |
US20200302556A1 (en) * | 2019-03-21 | 2020-09-24 | International Business Machines Corporation | Crop recommendation |
CN112149004A (en) * | 2020-10-30 | 2020-12-29 | 中国科学院计算技术研究所 | Personalized recommendation method based on collaborative knowledge map |
CN114461903A (en) * | 2021-12-29 | 2022-05-10 | 北京市农林科学院信息技术研究中心 | Method and device for determining suitable popularization area of crop variety |
CN114332667A (en) * | 2022-03-17 | 2022-04-12 | 北京市农林科学院信息技术研究中心 | Corn plant type identification method and device, electronic equipment and storage medium |
CN114595344A (en) * | 2022-05-09 | 2022-06-07 | 北京市农林科学院信息技术研究中心 | Crop variety management-oriented knowledge graph construction method and device |
Non-Patent Citations (2)
Title |
---|
于春花 等: "农作物品种试验数据管理平台设计与实现" * |
孙雨生;祝博;朱礼军;: "国内基于知识图谱的信息推荐研究进展" * |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115860581A (en) * | 2023-02-28 | 2023-03-28 | 北京市农林科学院信息技术研究中心 | Method, device, equipment and storage medium for evaluating suitability of crop variety |
CN116109915A (en) * | 2023-04-17 | 2023-05-12 | 济宁能源发展集团有限公司 | Intelligent recognition method for container door state |
CN116109915B (en) * | 2023-04-17 | 2023-07-18 | 济宁能源发展集团有限公司 | Intelligent recognition method for container door state |
CN117371529A (en) * | 2023-12-07 | 2024-01-09 | 北京市农林科学院信息技术研究中心 | Crop phenotype data knowledge graph generation method and device, electronic equipment and medium |
CN117371529B (en) * | 2023-12-07 | 2024-04-05 | 北京市农林科学院信息技术研究中心 | Crop phenotype data knowledge graph generation method and device, electronic equipment and medium |
CN117557399A (en) * | 2024-01-11 | 2024-02-13 | 四川省农村经济综合信息中心 | Salvia miltiorrhiza growth proper distribution area analysis system and analysis method thereof |
CN117557399B (en) * | 2024-01-11 | 2024-03-12 | 四川省农村经济综合信息中心 | Salvia miltiorrhiza growth proper distribution area analysis system and analysis method thereof |
Also Published As
Publication number | Publication date |
---|---|
CN115618021B (en) | 2023-04-28 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Gutiérrez et al. | A review of visualisations in agricultural decision support systems: An HCI perspective | |
CN115618021B (en) | Method and device for recommending planting area suitable for crop variety | |
CN109328016A (en) | Method for the hybrid species of plant breeding for identification | |
Arumugam | A predictive modeling approach for improving paddy crop productivity using data mining techniques | |
Willemen et al. | Spatial patterns of diversity and genetic erosion of traditional cassava (Manihot esculenta Crantz) in the Peruvian Amazon: An evaluation of socio-economic and environmental indicators | |
Mulla et al. | Crop-yield and price forecasting using machine learning | |
CN113139717B (en) | Crop seedling condition grading remote sensing monitoring method and device | |
CN113220827B (en) | Construction method and device of agricultural corpus | |
Hudait et al. | Site suitability assessment for traditional betel vine cultivation and crop acreage expansion in Tamluk Subdivision of Eastern India using AHP-based multi-criteria decision making approach | |
Fenz et al. | AI-and data-driven pre-crop values and crop rotation matrices | |
Nikoloski et al. | Farm reorientation assessment model based on multi-criteria decision making | |
Albayrak et al. | Development of intelligent decision support system using fuzzy cognitive maps for migratory beekeepers | |
Verma et al. | [Retracted] Plantosphere: Next Generation Adaptive and Smart Agriculture System | |
An et al. | Optimized supply chain management of rice in south korea: Location–allocation model of rice production | |
Perković et al. | Shallot species and subtypes discrimination based on morphology descriptors | |
Motia et al. | Ensemble classifier to support decisions on Soil Classification | |
US20230121145A1 (en) | Method of introducing ecosystem and method of managing value information about land | |
Diepeveen et al. | Identifying key crop performance traits using data mining. | |
CN117745148B (en) | Multi-source data-based rice stubble flue-cured tobacco planting quality evaluation method and system | |
Mulyani et al. | Clustering Productivity of Rice in Karawang Regency Using the Fuzzy C-Means Method | |
CN110263922A (en) | It is a kind of for evaluating the training data processing method of Grassland degradation degree | |
Mondo et al. | Farming practices, varietal preferences, and land suitability analyses for yam production in Eastern DR Congo: implications for breeding initiatives and food sovereignty | |
Nath et al. | Design of intelligent system in agriculture using data mining | |
Abiola et al. | Toward tailored interventions in plantain (Musa paradisiaca L.) industry: Insights from heterogeneity and constraints to plantain-based cropping systems in South-Benin | |
Amaral et al. | Application of Artificial Neural Networks to Predict Genotypic Values of Soybean Derived from Wide and Restricted Crosses for Relative Maturity Groups |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |